Bayes Theorem in Assessment of ADHD
Bayes theorem is a simple yet fundamental theorem in probability that states that P(A|B) = P(B|A) * P(A) / P(B), for two events A and B. What makes this theorem so powerful is its ability to describe the probability of an event based on some prior knowledge. This theorem thus has widespread applications across a variety of situations. We learned about this theorem in class as an important tool for understanding information cascades, which describe a phenomenon in which people end up making decisions based on the decisions of other people instead of following their own signal or impression.
Another interesting application of this theorem is discussed in the attached paper. In this work, the researchers use Bayesian inference for ADHD appraisal in female college students. They discuss how ADHD is currently appraised with various psychometric, EEG, and imaging tests, but these tests are not always accurate in their assessment. However, using classical Bayesian inference in a pilot study with 6 female controls and 6 females with ADHD, the assessment was able to classify all individuals correctly using combinations of psychometric tests and prior knowledge from both old and new EEG-based physiological markers of ADHD.
The fact that what seems like a simple mathematical concept is the foundation for modeling more complex phenomena like information cascades, and also can do incredible things such as improving our methods of appraising neurobehavioral disorders, demonstrates how the deceptively abstract concepts and phenomena we learn in this class have widespread applications to real world problems.